review-anvil-readonly
Pass
Audited by Gen Agent Trust Hub on May 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill acts as a thin configuration wrapper (preset) for another internal skill located at
../review-anvil/SKILL.md. It does not contain any executable code or standalone logic. - [SAFE]: The skill explicitly includes security-focused instructions ('Pin-rejection') designed to prevent users from overriding critical safety parameters, specifically ensuring the engine remains in a read-only mode.
- [SAFE]: No external downloads, remote code execution patterns, or data exfiltration vectors were identified. The skill operates entirely within the context of the local file system and internal skill references.
Audit Metadata